Deep-learning-based on-chip rapid spectral imaging with high spatial resolution

TL;DR

This paper presents a deep learning approach for on-chip spectral imaging that significantly accelerates spectral data reconstruction, eliminates mosaic effects, and enables real-time imaging for applications like autonomous driving.

Contribution

The study introduces a deep learning-based spectral data cube reconstruction method that vastly improves speed and accuracy over traditional iterative methods in on-chip spectral imaging.

Findings

Achieved four orders of magnitude faster spectral reconstruction.

Reconstructed spectral images with over 99% fidelity.

Enabled real-time video-rate spectral imaging for moving scenes.

Abstract

Spectral imaging extends the concept of traditional color cameras to capture images across multiple spectral channels and has broad application prospects. Conventional spectral cameras based on scanning methods suffer from low acquisition speed and large volume. On-chip computational spectral imaging based on metasurface filters provides a promising scheme for portable applications, but endures long computation time for point-by-point iterative spectral reconstruction and mosaic effect in the reconstructed spectral images. In this study, we demonstrated on-chip rapid spectral imaging eliminating the mosaic effect in the spectral image by deep-learning-based spectral data cube reconstruction. We experimentally achieved four orders of magnitude speed improvement than iterative spectral reconstruction and high fidelity of spectral reconstruction over 99% for a standard color board. In particular, we demonstrated video-rate spectral imaging for moving objects and outdoor driving scenes with good performance for recognizing metamerism, where the concolorous sky and white cars can be distinguished via their spectra, showing great potential for autonomous driving and other practical applications in the field of intelligent perception.